Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    exclamation points used for emphasis or excitement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.61
    <?
    -1.04
    ⓧ
    -1.04
    
    -1.01
    <?
    -1.00
    /***
    -0.94
    /**
    -0.94
    /*
    -0.85
    /*++
    -0.81
    ///**
    -0.80
    POSITIVE LOGITS
     maneu
    1.73
     affor
    1.58
     accla
    1.52
     philanth
    1.46
     increa
    1.45
     véhic
    1.43
     shenan
    1.41
     impra
    1.41
     disagre
    1.40
     reluct
    1.39
    Act Density 0.274%

    No Known Activations